The Illusion of Fairness: When Bias Mitigation Harms Clinical Performance in Imbalanced Healthcare Prediction

Zeinali, P & Zeinali, N

Available at SSRN: https://ssrn.com/abstract=6876214 or http://dx.doi.org/10.2139/ssrn.6876214

This study introduces and empirically characterizes the 'illusion of fairness'—a phenomenon wherein standard bias mitigation techniques appear to optimize statistical fairness metrics while simultaneously degrading overall predictive performance, destabilizing decision thresholds, and redistributing errors in clinically harmful ways across subgroups.

PDF (Open Access) Details Prepared by Medical & Health Sciences GroupMedical & Health Sciences Group

An interpretable unsupervised framework for exercise pattern discovery using wearable sensor data.

Zeinali, P., & Taluki, A. G

Journal of Trends of Health Information, Vol. 14, Issue 2, pp. 187-214 (March 2025)

This study uses the publicly available Wearable Sports Health Monitoring Dataset, consisting of 500 records collected from athletes during various activities, to identify latent exercise patterns based on physiological responses. An unsupervised clustering framework is proposed to categorize athletes into three exercise groups: short-duration high-intensity activity, long-duration low-intensity activity, and moderate activity.

PDF (Subscription Access) Details Prepared by AI & Computational Systems Group